User | iPhonedo |
Upload Date | March 03 2025 03:06 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.3.1 |
Model | iPhone 16 Plus |
Model ID | iPhone17,4 |
Motherboard | D48AP |
CPU Information | |
---|---|
Name | Apple A18 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1950
362.6 IPS |
|
Image Classification (HP)
|
100% |
15276
2.84 KIPS |
|
Image Classification (Q)
|
97% |
20531
3.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1804
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
18191
294.9 IPS |
|
Image Segmentation (Q)
|
99% |
23835
386.4 IPS |
|
Pose Estimation (SP)
|
100% |
8734
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
154714
180.5 IPS |
|
Pose Estimation (Q)
|
95% |
294931
345.7 IPS |
|
Object Detection (SP)
|
100% |
2107
167.2 IPS |
|
Object Detection (HP)
|
100% |
16229
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22525
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3310
39.3 IPS |
|
Face Detection (HP)
|
100% |
40610
482.5 IPS |
|
Face Detection (Q)
|
100% |
56256
668.4 IPS |
|
Depth Estimation (SP)
|
100% |
7463
57.5 IPS |
|
Depth Estimation (HP)
|
99% |
96827
746.0 IPS |
|
Depth Estimation (Q)
|
85% |
166016
1.30 KIPS |
|
Style Transfer (SP)
|
100% |
22751
29.2 IPS |
|
Style Transfer (HP)
|
100% |
246693
317.1 IPS |
|
Style Transfer (Q)
|
96% |
305721
394.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5229
193.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
52644
1.94 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86449
3.19 KIPS |
|
Text Classification (SP)
|
100% |
3497
4.67 KIPS |
|
Text Classification (HP)
|
100% |
4638
6.19 KIPS |
|
Text Classification (Q)
|
93% |
5022
6.74 KIPS |
|
Machine Translation (SP)
|
100% |
3454
59.5 IPS |
|
Machine Translation (HP)
|
100% |
10506
181.0 IPS |
|
Machine Translation (Q)
|
98% |
11615
200.7 IPS |